tokyotech llm Swallow 13b instruct v0.1 needs about 15.2 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 24 quants, from 3.0 GB (IQ1_S) to 14.0 GB (Q8_0).
Tokyotech Swallow 13b Instruct v0.1 – a 13 billion‑parameter Llama‑based instruction model
Swallow 13b Instruct v0.1 is a 13 billion‑parameter Llama architecture model trained on 4096‑token context. It is released under the llama2 license and is available in multiple GGUF quantizations. The model is designed for instruction following tasks.
Good at
- Instruction following
- Japanese language support
- Large context handling
Limits
- No vision support
- Requires 8 k context for estimates
- License restricts commercial use
Best for
- Chatbots needing 13 b context
- Fine‑tuning Japanese instruction models
- Research on large‑parameter Llama variants
Who it’s for. Developers and researchers who need a 13 billion‑parameter Llama model for instruction tasks. The model is suitable for those who can allocate sufficient GPU memory and are comfortable with GGUF quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 3.0 GB | 6.8 GB | Fits | Get file → | |
| IQ1_M | 3.2 GB | 7.1 GB | Fits | Get file → | |
| IQ2_XXS | 3.6 GB | 7.5 GB | Tight | Get file → | |
| IQ2_XS | 3.9 GB | 7.8 GB | Tight | Get file → | |
| IQ2_S | 4.3 GB | 8.1 GB | Too big | Get file → | |
| IQ2_M | 4.6 GB | 8.4 GB | Too big | Get file → | |
| Q2_K | 4.9 GB | 8.8 GB | Too big | Get file → | |
| IQ3_XXS | 5.0 GB | 8.9 GB | Too big | Get file → | |
| IQ3_XS | 5.4 GB | 9.3 GB | Too big | Get file → | |
| IQ3_S | 5.7 GB | 9.6 GB | Too big | Get file → | |
| Q3_K_S | 5.7 GB | 9.6 GB | Too big | Get file → | |
| IQ3_M | 6.1 GB | 9.9 GB | Too big | Get file → | |
| Q3_K_M | 6.4 GB | 10.3 GB | Too big | Get file → | |
| Q3_K_L | 7.0 GB | 10.9 GB | Too big | Get file → | |
| IQ4_XS | 7.0 GB | 10.9 GB | Too big | Get file → | |
| IQ4_NL | 7.4 GB | 11.3 GB | Too big | Get file → | |
| Q4_0 | 7.4 GB | 11.3 GB | Too big | Get file → | |
| Q4_K_S | 7.5 GB | 11.4 GB | Too big | Get file → | |
| Q4_K_M | 7.9 GB | 11.8 GB | Too big | Get file → | |
| Q5_0 | 9.1 GB | 12.9 GB | Too big | Get file → | |
| Q5_K_S | 9.1 GB | 12.9 GB | Too big | Get file → | |
| Q5_K_M | 9.3 GB | 13.2 GB | Too big | Get file → | |
| Q6_K | 10.8 GB | 14.6 GB | Too big | Get file → | |
| Q8_0 | 14.0 GB | 17.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.96 GB, ~10.2 GB RAM). For 16 GB VRAM, Q4_K_M (7.95 GB, ~15.2 GB RAM) is a good balance. For 24 GB VRAM, Q5_K_M (9.32 GB, ~16.5 GB RAM) offers higher quality.
What GPU do you need for tokyotech llm Swallow 13b instruct v0.1?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ2_M (4.6 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q4_K_M (7.9 GB file, about 15.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (14.0 GB file, about 21.2 GB in use).
Which tokyotech llm Swallow 13b instruct v0.1 quant should you choose?
Q4_K_M is the usual starting point for tokyotech llm Swallow 13b instruct v0.1: it balances file size and quality well. Here it is a 7.9 GB file.
The Q8_0 file is 14.0 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is IQ1_S at 3.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about tokyotech llm Swallow 13b instruct v0.1
How much VRAM does tokyotech llm Swallow 13b instruct v0.1 need?
About 15.2 GB at Q4_K_M with an 8K context window. That is the 7.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run tokyotech llm Swallow 13b instruct v0.1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 10.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of tokyotech llm Swallow 13b instruct v0.1 GGUF?
It depends on the quant: IQ1_S is 3.0 GB, IQ1_M is 3.2 GB, IQ2_XXS is 3.6 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.3 GB, IQ2_M is 4.6 GB and 18 more.
What context length does tokyotech llm Swallow 13b instruct v0.1 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 6.7 GB at 8K and 3.4 GB at 4K.
Where can I download tokyotech llm Swallow 13b instruct v0.1 GGUF?
The files are on Hugging Face in the mmnga/tokyotech-llm-Swallow-13b-instruct-v0.1-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does tokyotech llm Swallow 13b instruct v0.1 use?
Hugging Face lists the license as llama2. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Swallow 13b on 8 GB VRAM?
Use the IQ1_S quantization; it requires about 10.2 GB RAM at 8 k context, which fits 8 GB VRAM with some headroom.
Does this model support vision tasks?
No, the model has no vision capabilities; it is text‑only.
What license applies to this model?
The model is released under the llama2 license, which allows non‑commercial use and requires attribution.